Skip to content
@xlang-ai

XLANG NLP Lab

Building language model agents that ground language instructions into code or actions executable in real-world environments

Welcome to the Executable Language Grounding (XLANG) Lab! We are part of the HKU NLP Group at the University of Hong Kong. XLang focuses on building language model agents that transform (“grounding”) language instructions into code or actions executable in real-world environments, including databases (data agent), web applications (plugins/web agent), and the physical world (robotic agent) etc,. It lies at the heart of language model agents or natural language interfaces that can interact with and learn from these real-world environments to facilitate human interaction with data analysis, web applications, and robotic instruction through conversation. Recent advances in XLang incorporate techniques such as LLM + external tools, code generation, semantic parsing, and dialog or interactive systems.

Pinned Loading

  1. OSWorld OSWorld Public

    OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

    Python 1.1k 131

  2. OpenAgents OpenAgents Public

    [COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild

    Python 3.9k 425

  3. instructor-embedding instructor-embedding Public

    [ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

    Python 1.8k 136

  4. text2reward text2reward Public

    [ICLR 2024] Code for the paper "Text2Reward: Automated Dense Reward Function Generation for Reinforcement Learning"

    Jupyter Notebook 113 6

  5. Binder Binder Public

    [ICLR 2023] Code for the paper "Binding Language Models in Symbolic Languages"

    Python 294 33

  6. DS-1000 DS-1000 Public

    [ICML 2023] Data and code release for the paper "DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation".

    Python 212 25

Repositories

Showing 10 of 16 repositories
  • Spider2 Public

    Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

    xlang-ai/Spider2’s past year of commit activity
    Python 55 Apache-2.0 0 0 0 Updated Sep 9, 2024
  • Spider2-V Public

    Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

    xlang-ai/Spider2-V’s past year of commit activity
    Jupyter Notebook 98 Apache-2.0 5 1 0 Updated Aug 26, 2024
  • instructor-embedding Public

    [ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

    xlang-ai/instructor-embedding’s past year of commit activity
    Python 1,832 Apache-2.0 136 31 1 Updated Aug 26, 2024
  • OSWorld Public

    OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

    xlang-ai/OSWorld’s past year of commit activity
    Python 1,116 Apache-2.0 131 13 0 Updated Aug 23, 2024
  • DS-1000 Public

    [ICML 2023] Data and code release for the paper "DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation".

    xlang-ai/DS-1000’s past year of commit activity
    Python 212 CC-BY-SA-4.0 25 2 0 Updated Aug 10, 2024
  • BRIGHT Public

    BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

    xlang-ai/BRIGHT’s past year of commit activity
    Python 40 CC-BY-4.0 0 0 0 Updated Jul 23, 2024
  • OpenAgents Public

    [COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild

    xlang-ai/OpenAgents’s past year of commit activity
    Python 3,887 Apache-2.0 425 10 2 Updated Jul 8, 2024
  • arks Public
    xlang-ai/arks’s past year of commit activity
    Python 48 Apache-2.0 6 3 0 Updated Jun 16, 2024
  • xlang-paper-reading Public

    Paper collection on building and evaluating language model agents via executable language grounding

    xlang-ai/xlang-paper-reading’s past year of commit activity
    333 12 0 0 Updated Apr 29, 2024
  • batch-prompting Public

    [EMNLP 2023 Industry Track] A simple prompting approach that enables the LLMs to run inference in batches.

    xlang-ai/batch-prompting’s past year of commit activity
    Python 64 5 1 1 Updated Mar 8, 2024